Gencode-BPE / checkpoint-375 /trainer_state.json
andyjzhao's picture
Upload folder using huggingface_hub
f6eeed7 verified
{
"best_global_step": 375,
"best_metric": 6.038269996643066,
"best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/Gencode-BPE/checkpoint-375",
"epoch": 0.10638297872340426,
"eval_steps": 125,
"global_step": 375,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005673758865248227,
"grad_norm": 1275.0146484375,
"loss": 281.4781,
"lr": 2e-06,
"step": 2,
"tokens_trained": 0.000192256
},
{
"epoch": 0.0011347517730496454,
"grad_norm": 1437.579833984375,
"loss": 267.2211,
"lr": 6e-06,
"step": 4,
"tokens_trained": 0.000382024
},
{
"epoch": 0.001702127659574468,
"grad_norm": 1719.271484375,
"loss": 219.3822,
"lr": 1e-05,
"step": 6,
"tokens_trained": 0.00057072
},
{
"epoch": 0.0022695035460992908,
"grad_norm": 1444.94970703125,
"loss": 133.8172,
"lr": 1.4e-05,
"step": 8,
"tokens_trained": 0.000761336
},
{
"epoch": 0.0028368794326241137,
"grad_norm": 238.9689178466797,
"loss": 90.8177,
"lr": 1.8e-05,
"step": 10,
"tokens_trained": 0.000953248
},
{
"epoch": 0.003404255319148936,
"grad_norm": 158.53497314453125,
"loss": 84.6922,
"lr": 2.2e-05,
"step": 12,
"tokens_trained": 0.00114424
},
{
"epoch": 0.003971631205673759,
"grad_norm": 146.10595703125,
"loss": 76.7055,
"lr": 2.6e-05,
"step": 14,
"tokens_trained": 0.001334104
},
{
"epoch": 0.0045390070921985815,
"grad_norm": 140.69964599609375,
"loss": 67.9952,
"lr": 3e-05,
"step": 16,
"tokens_trained": 0.00152392
},
{
"epoch": 0.005106382978723404,
"grad_norm": 108.80303192138672,
"loss": 57.8088,
"lr": 3.4000000000000007e-05,
"step": 18,
"tokens_trained": 0.001713872
},
{
"epoch": 0.005673758865248227,
"grad_norm": 106.82334899902344,
"loss": 48.6585,
"lr": 3.8e-05,
"step": 20,
"tokens_trained": 0.001903976
},
{
"epoch": 0.00624113475177305,
"grad_norm": 93.58769989013672,
"loss": 41.7984,
"lr": 4.2000000000000004e-05,
"step": 22,
"tokens_trained": 0.002094288
},
{
"epoch": 0.006808510638297872,
"grad_norm": 87.5854721069336,
"loss": 37.6201,
"lr": 4.6e-05,
"step": 24,
"tokens_trained": 0.002282496
},
{
"epoch": 0.007375886524822695,
"grad_norm": 84.12794494628906,
"loss": 35.0091,
"lr": 5e-05,
"step": 26,
"tokens_trained": 0.00247068
},
{
"epoch": 0.007943262411347518,
"grad_norm": 79.77535247802734,
"loss": 33.2253,
"lr": 5.4e-05,
"step": 28,
"tokens_trained": 0.002662888
},
{
"epoch": 0.00851063829787234,
"grad_norm": 66.42157745361328,
"loss": 32.0682,
"lr": 5.800000000000001e-05,
"step": 30,
"tokens_trained": 0.002851968
},
{
"epoch": 0.009078014184397163,
"grad_norm": 87.52485656738281,
"loss": 30.893,
"lr": 6.2e-05,
"step": 32,
"tokens_trained": 0.003041384
},
{
"epoch": 0.009645390070921986,
"grad_norm": 58.33614730834961,
"loss": 30.0513,
"lr": 6.6e-05,
"step": 34,
"tokens_trained": 0.003232872
},
{
"epoch": 0.010212765957446808,
"grad_norm": 54.629329681396484,
"loss": 29.0115,
"lr": 7.000000000000001e-05,
"step": 36,
"tokens_trained": 0.003423824
},
{
"epoch": 0.01078014184397163,
"grad_norm": 52.79097366333008,
"loss": 28.2084,
"lr": 7.4e-05,
"step": 38,
"tokens_trained": 0.003613232
},
{
"epoch": 0.011347517730496455,
"grad_norm": 54.481224060058594,
"loss": 27.4345,
"lr": 7.8e-05,
"step": 40,
"tokens_trained": 0.003800952
},
{
"epoch": 0.011914893617021277,
"grad_norm": 58.7069091796875,
"loss": 26.5936,
"lr": 8.2e-05,
"step": 42,
"tokens_trained": 0.003991512
},
{
"epoch": 0.0124822695035461,
"grad_norm": 49.30760955810547,
"loss": 26.0608,
"lr": 8.599999999999999e-05,
"step": 44,
"tokens_trained": 0.004180648
},
{
"epoch": 0.013049645390070922,
"grad_norm": 61.902587890625,
"loss": 25.5363,
"lr": 8.999999999999999e-05,
"step": 46,
"tokens_trained": 0.00437148
},
{
"epoch": 0.013617021276595745,
"grad_norm": 46.76111602783203,
"loss": 24.9599,
"lr": 9.400000000000001e-05,
"step": 48,
"tokens_trained": 0.004559344
},
{
"epoch": 0.014184397163120567,
"grad_norm": 57.06416702270508,
"loss": 24.4087,
"lr": 9.800000000000001e-05,
"step": 50,
"tokens_trained": 0.004749256
},
{
"epoch": 0.01475177304964539,
"grad_norm": 44.798736572265625,
"loss": 24.1444,
"lr": 0.000102,
"step": 52,
"tokens_trained": 0.004940192
},
{
"epoch": 0.015319148936170212,
"grad_norm": 40.29296875,
"loss": 23.6011,
"lr": 0.000106,
"step": 54,
"tokens_trained": 0.005130304
},
{
"epoch": 0.015886524822695036,
"grad_norm": 38.75099563598633,
"loss": 23.1781,
"lr": 0.00011,
"step": 56,
"tokens_trained": 0.005322864
},
{
"epoch": 0.016453900709219857,
"grad_norm": 37.470706939697266,
"loss": 22.9136,
"lr": 0.000114,
"step": 58,
"tokens_trained": 0.00551392
},
{
"epoch": 0.01702127659574468,
"grad_norm": 35.1894645690918,
"loss": 22.6336,
"lr": 0.000118,
"step": 60,
"tokens_trained": 0.005703096
},
{
"epoch": 0.017588652482269502,
"grad_norm": 35.136573791503906,
"loss": 22.2998,
"lr": 0.000122,
"step": 62,
"tokens_trained": 0.005892448
},
{
"epoch": 0.018156028368794326,
"grad_norm": 38.05111312866211,
"loss": 21.9401,
"lr": 0.000126,
"step": 64,
"tokens_trained": 0.006081656
},
{
"epoch": 0.01872340425531915,
"grad_norm": 35.63850021362305,
"loss": 21.7206,
"lr": 0.00013000000000000002,
"step": 66,
"tokens_trained": 0.006273032
},
{
"epoch": 0.01929078014184397,
"grad_norm": 34.327667236328125,
"loss": 21.4051,
"lr": 0.000134,
"step": 68,
"tokens_trained": 0.00646304
},
{
"epoch": 0.019858156028368795,
"grad_norm": 31.457059860229492,
"loss": 21.0774,
"lr": 0.00013800000000000002,
"step": 70,
"tokens_trained": 0.006652832
},
{
"epoch": 0.020425531914893616,
"grad_norm": 34.91672897338867,
"loss": 20.8718,
"lr": 0.00014199999999999998,
"step": 72,
"tokens_trained": 0.006843512
},
{
"epoch": 0.02099290780141844,
"grad_norm": 27.959579467773438,
"loss": 20.6932,
"lr": 0.000146,
"step": 74,
"tokens_trained": 0.007033584
},
{
"epoch": 0.02156028368794326,
"grad_norm": 26.569866180419922,
"loss": 20.4072,
"lr": 0.00015,
"step": 76,
"tokens_trained": 0.007224032
},
{
"epoch": 0.022127659574468085,
"grad_norm": 28.009904861450195,
"loss": 20.2229,
"lr": 0.000154,
"step": 78,
"tokens_trained": 0.00741368
},
{
"epoch": 0.02269503546099291,
"grad_norm": 28.892959594726562,
"loss": 20.0528,
"lr": 0.000158,
"step": 80,
"tokens_trained": 0.00760416
},
{
"epoch": 0.02326241134751773,
"grad_norm": 31.58131980895996,
"loss": 19.8016,
"lr": 0.000162,
"step": 82,
"tokens_trained": 0.007793952
},
{
"epoch": 0.023829787234042554,
"grad_norm": 31.01254653930664,
"loss": 19.634,
"lr": 0.00016600000000000002,
"step": 84,
"tokens_trained": 0.007980792
},
{
"epoch": 0.024397163120567375,
"grad_norm": 28.732515335083008,
"loss": 19.3777,
"lr": 0.00017,
"step": 86,
"tokens_trained": 0.008171968
},
{
"epoch": 0.0249645390070922,
"grad_norm": 24.31264877319336,
"loss": 19.1346,
"lr": 0.000174,
"step": 88,
"tokens_trained": 0.008361632
},
{
"epoch": 0.02553191489361702,
"grad_norm": 26.557010650634766,
"loss": 19.0014,
"lr": 0.000178,
"step": 90,
"tokens_trained": 0.008552328
},
{
"epoch": 0.026099290780141844,
"grad_norm": 21.156103134155273,
"loss": 18.7032,
"lr": 0.000182,
"step": 92,
"tokens_trained": 0.008743136
},
{
"epoch": 0.02666666666666667,
"grad_norm": 25.7484188079834,
"loss": 18.4836,
"lr": 0.000186,
"step": 94,
"tokens_trained": 0.008932056
},
{
"epoch": 0.02723404255319149,
"grad_norm": 22.27949333190918,
"loss": 18.2233,
"lr": 0.00019,
"step": 96,
"tokens_trained": 0.009121608
},
{
"epoch": 0.027801418439716313,
"grad_norm": 24.9247989654541,
"loss": 17.9867,
"lr": 0.000194,
"step": 98,
"tokens_trained": 0.009311008
},
{
"epoch": 0.028368794326241134,
"grad_norm": 24.302066802978516,
"loss": 17.8016,
"lr": 0.00019800000000000002,
"step": 100,
"tokens_trained": 0.009501456
},
{
"epoch": 0.02893617021276596,
"grad_norm": 23.458459854125977,
"loss": 17.6295,
"lr": 0.000202,
"step": 102,
"tokens_trained": 0.009693952
},
{
"epoch": 0.02950354609929078,
"grad_norm": 24.092350006103516,
"loss": 17.4593,
"lr": 0.000206,
"step": 104,
"tokens_trained": 0.009883328
},
{
"epoch": 0.030070921985815603,
"grad_norm": 22.54726219177246,
"loss": 17.2141,
"lr": 0.00021,
"step": 106,
"tokens_trained": 0.01007316
},
{
"epoch": 0.030638297872340424,
"grad_norm": 21.334760665893555,
"loss": 17.044,
"lr": 0.000214,
"step": 108,
"tokens_trained": 0.010266504
},
{
"epoch": 0.031205673758865248,
"grad_norm": 20.584287643432617,
"loss": 16.8919,
"lr": 0.000218,
"step": 110,
"tokens_trained": 0.010455736
},
{
"epoch": 0.03177304964539007,
"grad_norm": 23.51676368713379,
"loss": 16.751,
"lr": 0.000222,
"step": 112,
"tokens_trained": 0.010645208
},
{
"epoch": 0.03234042553191489,
"grad_norm": 23.278276443481445,
"loss": 16.5997,
"lr": 0.00022600000000000002,
"step": 114,
"tokens_trained": 0.010838928
},
{
"epoch": 0.032907801418439714,
"grad_norm": 25.4830265045166,
"loss": 16.3416,
"lr": 0.00023,
"step": 116,
"tokens_trained": 0.011027792
},
{
"epoch": 0.03347517730496454,
"grad_norm": 29.442413330078125,
"loss": 16.24,
"lr": 0.00023400000000000002,
"step": 118,
"tokens_trained": 0.011217456
},
{
"epoch": 0.03404255319148936,
"grad_norm": 21.77578353881836,
"loss": 16.1922,
"lr": 0.00023799999999999998,
"step": 120,
"tokens_trained": 0.01140804
},
{
"epoch": 0.03460992907801418,
"grad_norm": 27.040719985961914,
"loss": 15.9059,
"lr": 0.000242,
"step": 122,
"tokens_trained": 0.011597816
},
{
"epoch": 0.035177304964539004,
"grad_norm": 24.74480628967285,
"loss": 15.7818,
"lr": 0.000246,
"step": 124,
"tokens_trained": 0.011785624
},
{
"epoch": 0.03546099290780142,
"eval_loss": 15.553059577941895,
"eval_runtime": 23.5485,
"step": 125,
"tokens_trained": 0.011880832
},
{
"epoch": 0.03574468085106383,
"grad_norm": 23.13482666015625,
"loss": 15.5739,
"lr": 0.00025,
"step": 126,
"tokens_trained": 0.011975976
},
{
"epoch": 0.03631205673758865,
"grad_norm": 22.8618106842041,
"loss": 15.4302,
"lr": 0.000254,
"step": 128,
"tokens_trained": 0.012166744
},
{
"epoch": 0.03687943262411347,
"grad_norm": 26.804859161376953,
"loss": 15.3623,
"lr": 0.00025800000000000004,
"step": 130,
"tokens_trained": 0.01235436
},
{
"epoch": 0.0374468085106383,
"grad_norm": 21.826601028442383,
"loss": 15.1465,
"lr": 0.000262,
"step": 132,
"tokens_trained": 0.012544976
},
{
"epoch": 0.03801418439716312,
"grad_norm": 39.447086334228516,
"loss": 15.0137,
"lr": 0.000266,
"step": 134,
"tokens_trained": 0.012736352
},
{
"epoch": 0.03858156028368794,
"grad_norm": 23.44275665283203,
"loss": 14.9355,
"lr": 0.00027,
"step": 136,
"tokens_trained": 0.012925008
},
{
"epoch": 0.03914893617021276,
"grad_norm": 21.631427764892578,
"loss": 14.6825,
"lr": 0.00027400000000000005,
"step": 138,
"tokens_trained": 0.013114672
},
{
"epoch": 0.03971631205673759,
"grad_norm": 23.674650192260742,
"loss": 14.5194,
"lr": 0.00027800000000000004,
"step": 140,
"tokens_trained": 0.013304016
},
{
"epoch": 0.04028368794326241,
"grad_norm": 23.974796295166016,
"loss": 14.4829,
"lr": 0.00028199999999999997,
"step": 142,
"tokens_trained": 0.013496696
},
{
"epoch": 0.04085106382978723,
"grad_norm": 26.112201690673828,
"loss": 14.3027,
"lr": 0.00028599999999999996,
"step": 144,
"tokens_trained": 0.013684816
},
{
"epoch": 0.04141843971631206,
"grad_norm": 20.67386817932129,
"loss": 14.1499,
"lr": 0.00029,
"step": 146,
"tokens_trained": 0.013874832
},
{
"epoch": 0.04198581560283688,
"grad_norm": 24.253408432006836,
"loss": 13.9378,
"lr": 0.000294,
"step": 148,
"tokens_trained": 0.014065056
},
{
"epoch": 0.0425531914893617,
"grad_norm": 35.716087341308594,
"loss": 14.0562,
"lr": 0.000298,
"step": 150,
"tokens_trained": 0.014256784
},
{
"epoch": 0.04312056737588652,
"grad_norm": 29.414331436157227,
"loss": 14.0462,
"lr": 0.000302,
"step": 152,
"tokens_trained": 0.014446312
},
{
"epoch": 0.04368794326241135,
"grad_norm": 30.687482833862305,
"loss": 13.7603,
"lr": 0.000306,
"step": 154,
"tokens_trained": 0.014639872
},
{
"epoch": 0.04425531914893617,
"grad_norm": 29.806455612182617,
"loss": 13.708,
"lr": 0.00031,
"step": 156,
"tokens_trained": 0.014831112
},
{
"epoch": 0.04482269503546099,
"grad_norm": 24.900897979736328,
"loss": 13.548,
"lr": 0.000314,
"step": 158,
"tokens_trained": 0.015021288
},
{
"epoch": 0.04539007092198582,
"grad_norm": 24.29252815246582,
"loss": 13.3119,
"lr": 0.00031800000000000003,
"step": 160,
"tokens_trained": 0.01521228
},
{
"epoch": 0.04595744680851064,
"grad_norm": 20.68342399597168,
"loss": 13.1829,
"lr": 0.000322,
"step": 162,
"tokens_trained": 0.015403688
},
{
"epoch": 0.04652482269503546,
"grad_norm": 20.822795867919922,
"loss": 12.9044,
"lr": 0.000326,
"step": 164,
"tokens_trained": 0.015593416
},
{
"epoch": 0.04709219858156028,
"grad_norm": 21.689916610717773,
"loss": 12.6862,
"lr": 0.00033,
"step": 166,
"tokens_trained": 0.015784408
},
{
"epoch": 0.04765957446808511,
"grad_norm": 17.873889923095703,
"loss": 12.5502,
"lr": 0.00033400000000000004,
"step": 168,
"tokens_trained": 0.0159744
},
{
"epoch": 0.04822695035460993,
"grad_norm": 18.951616287231445,
"loss": 12.308,
"lr": 0.00033800000000000003,
"step": 170,
"tokens_trained": 0.016163736
},
{
"epoch": 0.04879432624113475,
"grad_norm": 15.146363258361816,
"loss": 12.1558,
"lr": 0.000342,
"step": 172,
"tokens_trained": 0.016353832
},
{
"epoch": 0.04936170212765958,
"grad_norm": 18.336984634399414,
"loss": 12.0386,
"lr": 0.000346,
"step": 174,
"tokens_trained": 0.016545088
},
{
"epoch": 0.0499290780141844,
"grad_norm": 17.221126556396484,
"loss": 11.8791,
"lr": 0.00035,
"step": 176,
"tokens_trained": 0.016735704
},
{
"epoch": 0.05049645390070922,
"grad_norm": 19.362564086914062,
"loss": 11.7224,
"lr": 0.000354,
"step": 178,
"tokens_trained": 0.016927944
},
{
"epoch": 0.05106382978723404,
"grad_norm": 15.564507484436035,
"loss": 11.6448,
"lr": 0.000358,
"step": 180,
"tokens_trained": 0.017116096
},
{
"epoch": 0.05163120567375887,
"grad_norm": 20.711383819580078,
"loss": 11.4398,
"lr": 0.000362,
"step": 182,
"tokens_trained": 0.01730564
},
{
"epoch": 0.05219858156028369,
"grad_norm": 18.627403259277344,
"loss": 11.3377,
"lr": 0.000366,
"step": 184,
"tokens_trained": 0.017495864
},
{
"epoch": 0.05276595744680851,
"grad_norm": 15.00942325592041,
"loss": 11.1416,
"lr": 0.00037,
"step": 186,
"tokens_trained": 0.017686464
},
{
"epoch": 0.05333333333333334,
"grad_norm": 17.070598602294922,
"loss": 11.0148,
"lr": 0.000374,
"step": 188,
"tokens_trained": 0.017879488
},
{
"epoch": 0.05390070921985816,
"grad_norm": 16.101457595825195,
"loss": 10.8874,
"lr": 0.000378,
"step": 190,
"tokens_trained": 0.018068312
},
{
"epoch": 0.05446808510638298,
"grad_norm": 15.613334655761719,
"loss": 10.7055,
"lr": 0.000382,
"step": 192,
"tokens_trained": 0.018255752
},
{
"epoch": 0.0550354609929078,
"grad_norm": 17.671857833862305,
"loss": 10.5706,
"lr": 0.000386,
"step": 194,
"tokens_trained": 0.018447096
},
{
"epoch": 0.05560283687943263,
"grad_norm": 16.080909729003906,
"loss": 10.4476,
"lr": 0.00039000000000000005,
"step": 196,
"tokens_trained": 0.018637264
},
{
"epoch": 0.05617021276595745,
"grad_norm": 15.02849292755127,
"loss": 10.2962,
"lr": 0.00039400000000000004,
"step": 198,
"tokens_trained": 0.018827552
},
{
"epoch": 0.05673758865248227,
"grad_norm": 14.990167617797852,
"loss": 10.1912,
"lr": 0.000398,
"step": 200,
"tokens_trained": 0.019018
},
{
"epoch": 0.05730496453900709,
"grad_norm": 15.390633583068848,
"loss": 10.0442,
"lr": 0.000402,
"step": 202,
"tokens_trained": 0.019209864
},
{
"epoch": 0.05787234042553192,
"grad_norm": 16.871570587158203,
"loss": 9.9685,
"lr": 0.00040600000000000006,
"step": 204,
"tokens_trained": 0.019400176
},
{
"epoch": 0.05843971631205674,
"grad_norm": 20.16544532775879,
"loss": 9.8531,
"lr": 0.00041,
"step": 206,
"tokens_trained": 0.019589424
},
{
"epoch": 0.05900709219858156,
"grad_norm": 16.825023651123047,
"loss": 9.7777,
"lr": 0.000414,
"step": 208,
"tokens_trained": 0.019779112
},
{
"epoch": 0.059574468085106386,
"grad_norm": 16.43510627746582,
"loss": 9.6122,
"lr": 0.00041799999999999997,
"step": 210,
"tokens_trained": 0.019970048
},
{
"epoch": 0.060141843971631206,
"grad_norm": 17.340473175048828,
"loss": 9.4859,
"lr": 0.000422,
"step": 212,
"tokens_trained": 0.020160968
},
{
"epoch": 0.06070921985815603,
"grad_norm": 15.019119262695312,
"loss": 9.3656,
"lr": 0.000426,
"step": 214,
"tokens_trained": 0.020349664
},
{
"epoch": 0.06127659574468085,
"grad_norm": 13.379194259643555,
"loss": 9.2348,
"lr": 0.00043,
"step": 216,
"tokens_trained": 0.020538192
},
{
"epoch": 0.061843971631205676,
"grad_norm": 16.71472930908203,
"loss": 9.2258,
"lr": 0.00043400000000000003,
"step": 218,
"tokens_trained": 0.020728936
},
{
"epoch": 0.062411347517730496,
"grad_norm": 12.743139266967773,
"loss": 9.0569,
"lr": 0.000438,
"step": 220,
"tokens_trained": 0.020917472
},
{
"epoch": 0.06297872340425532,
"grad_norm": 15.739934921264648,
"loss": 8.9623,
"lr": 0.000442,
"step": 222,
"tokens_trained": 0.02110928
},
{
"epoch": 0.06354609929078014,
"grad_norm": 14.23620891571045,
"loss": 8.8201,
"lr": 0.000446,
"step": 224,
"tokens_trained": 0.021300168
},
{
"epoch": 0.06411347517730497,
"grad_norm": 13.005538940429688,
"loss": 8.7235,
"lr": 0.00045000000000000004,
"step": 226,
"tokens_trained": 0.021490272
},
{
"epoch": 0.06468085106382979,
"grad_norm": 17.17629051208496,
"loss": 8.6907,
"lr": 0.00045400000000000003,
"step": 228,
"tokens_trained": 0.021681552
},
{
"epoch": 0.06524822695035461,
"grad_norm": 14.430739402770996,
"loss": 8.6196,
"lr": 0.000458,
"step": 230,
"tokens_trained": 0.02187236
},
{
"epoch": 0.06581560283687943,
"grad_norm": 14.575714111328125,
"loss": 8.4741,
"lr": 0.000462,
"step": 232,
"tokens_trained": 0.022061976
},
{
"epoch": 0.06638297872340425,
"grad_norm": 13.892754554748535,
"loss": 8.4118,
"lr": 0.00046600000000000005,
"step": 234,
"tokens_trained": 0.022252008
},
{
"epoch": 0.06695035460992908,
"grad_norm": 11.58240795135498,
"loss": 8.2781,
"lr": 0.00047,
"step": 236,
"tokens_trained": 0.02244284
},
{
"epoch": 0.0675177304964539,
"grad_norm": 13.022644996643066,
"loss": 8.2139,
"lr": 0.000474,
"step": 238,
"tokens_trained": 0.022631152
},
{
"epoch": 0.06808510638297872,
"grad_norm": 11.844677925109863,
"loss": 8.1134,
"lr": 0.00047799999999999996,
"step": 240,
"tokens_trained": 0.022821096
},
{
"epoch": 0.06865248226950355,
"grad_norm": 13.878067016601562,
"loss": 8.0221,
"lr": 0.000482,
"step": 242,
"tokens_trained": 0.023011656
},
{
"epoch": 0.06921985815602837,
"grad_norm": 12.34648323059082,
"loss": 7.9755,
"lr": 0.000486,
"step": 244,
"tokens_trained": 0.023201
},
{
"epoch": 0.06978723404255319,
"grad_norm": 14.238297462463379,
"loss": 7.8969,
"lr": 0.00049,
"step": 246,
"tokens_trained": 0.023391128
},
{
"epoch": 0.07035460992907801,
"grad_norm": 14.386019706726074,
"loss": 7.8627,
"lr": 0.000494,
"step": 248,
"tokens_trained": 0.023581768
},
{
"epoch": 0.07092198581560284,
"grad_norm": 13.623086929321289,
"loss": 7.7568,
"lr": 0.000498,
"step": 250,
"tokens_trained": 0.023771248
},
{
"epoch": 0.07092198581560284,
"eval_loss": 7.70297384262085,
"eval_runtime": 21.3853,
"step": 250,
"tokens_trained": 0.023771248
},
{
"epoch": 0.07148936170212766,
"grad_norm": 14.347646713256836,
"loss": 7.6842,
"lr": 0.0005020000000000001,
"step": 252,
"tokens_trained": 0.023961056
},
{
"epoch": 0.07205673758865248,
"grad_norm": 12.5592041015625,
"loss": 7.6516,
"lr": 0.000506,
"step": 254,
"tokens_trained": 0.024150968
},
{
"epoch": 0.0726241134751773,
"grad_norm": 13.219141960144043,
"loss": 7.5789,
"lr": 0.00051,
"step": 256,
"tokens_trained": 0.024340072
},
{
"epoch": 0.07319148936170213,
"grad_norm": 12.654081344604492,
"loss": 7.5369,
"lr": 0.000514,
"step": 258,
"tokens_trained": 0.024529296
},
{
"epoch": 0.07375886524822695,
"grad_norm": 13.136971473693848,
"loss": 7.4949,
"lr": 0.000518,
"step": 260,
"tokens_trained": 0.024719688
},
{
"epoch": 0.07432624113475177,
"grad_norm": 12.680288314819336,
"loss": 7.3904,
"lr": 0.000522,
"step": 262,
"tokens_trained": 0.024909632
},
{
"epoch": 0.0748936170212766,
"grad_norm": 12.754518508911133,
"loss": 7.3514,
"lr": 0.000526,
"step": 264,
"tokens_trained": 0.025098416
},
{
"epoch": 0.07546099290780142,
"grad_norm": 13.22311019897461,
"loss": 7.2951,
"lr": 0.0005300000000000001,
"step": 266,
"tokens_trained": 0.025287344
},
{
"epoch": 0.07602836879432624,
"grad_norm": 12.11903190612793,
"loss": 7.2229,
"lr": 0.0005340000000000001,
"step": 268,
"tokens_trained": 0.025477152
},
{
"epoch": 0.07659574468085106,
"grad_norm": 13.771833419799805,
"loss": 7.1815,
"lr": 0.0005380000000000001,
"step": 270,
"tokens_trained": 0.025668288
},
{
"epoch": 0.07716312056737588,
"grad_norm": 11.756864547729492,
"loss": 7.1669,
"lr": 0.0005420000000000001,
"step": 272,
"tokens_trained": 0.025858528
},
{
"epoch": 0.0777304964539007,
"grad_norm": 13.613094329833984,
"loss": 7.1079,
"lr": 0.000546,
"step": 274,
"tokens_trained": 0.026048616
},
{
"epoch": 0.07829787234042553,
"grad_norm": 10.001923561096191,
"loss": 7.0508,
"lr": 0.00055,
"step": 276,
"tokens_trained": 0.026236944
},
{
"epoch": 0.07886524822695036,
"grad_norm": 14.262083053588867,
"loss": 6.9955,
"lr": 0.000554,
"step": 278,
"tokens_trained": 0.026426848
},
{
"epoch": 0.07943262411347518,
"grad_norm": 12.381136894226074,
"loss": 6.9831,
"lr": 0.000558,
"step": 280,
"tokens_trained": 0.026616784
},
{
"epoch": 0.08,
"grad_norm": 9.815845489501953,
"loss": 6.917,
"lr": 0.0005620000000000001,
"step": 282,
"tokens_trained": 0.026805176
},
{
"epoch": 0.08056737588652482,
"grad_norm": 11.669997215270996,
"loss": 6.8999,
"lr": 0.000566,
"step": 284,
"tokens_trained": 0.02699488
},
{
"epoch": 0.08113475177304964,
"grad_norm": 12.770941734313965,
"loss": 6.8998,
"lr": 0.00057,
"step": 286,
"tokens_trained": 0.027185784
},
{
"epoch": 0.08170212765957446,
"grad_norm": 15.572457313537598,
"loss": 6.841,
"lr": 0.000574,
"step": 288,
"tokens_trained": 0.027375896
},
{
"epoch": 0.08226950354609928,
"grad_norm": 10.980833053588867,
"loss": 6.8545,
"lr": 0.000578,
"step": 290,
"tokens_trained": 0.02756588
},
{
"epoch": 0.08283687943262412,
"grad_norm": 11.678337097167969,
"loss": 6.7853,
"lr": 0.0005819999999999999,
"step": 292,
"tokens_trained": 0.02775456
},
{
"epoch": 0.08340425531914894,
"grad_norm": 9.77885913848877,
"loss": 6.7465,
"lr": 0.0005859999999999999,
"step": 294,
"tokens_trained": 0.027942856
},
{
"epoch": 0.08397163120567376,
"grad_norm": 13.62730884552002,
"loss": 6.7276,
"lr": 0.00059,
"step": 296,
"tokens_trained": 0.028133152
},
{
"epoch": 0.08453900709219858,
"grad_norm": 10.644404411315918,
"loss": 6.6802,
"lr": 0.000594,
"step": 298,
"tokens_trained": 0.028322192
},
{
"epoch": 0.0851063829787234,
"grad_norm": 11.130610466003418,
"loss": 6.6548,
"lr": 0.000598,
"step": 300,
"tokens_trained": 0.0285122
},
{
"epoch": 0.08567375886524822,
"grad_norm": 11.557455062866211,
"loss": 6.6155,
"lr": 0.000602,
"step": 302,
"tokens_trained": 0.028699792
},
{
"epoch": 0.08624113475177304,
"grad_norm": 9.276884078979492,
"loss": 6.5989,
"lr": 0.000606,
"step": 304,
"tokens_trained": 0.028889896
},
{
"epoch": 0.08680851063829788,
"grad_norm": 9.616179466247559,
"loss": 6.5773,
"lr": 0.00061,
"step": 306,
"tokens_trained": 0.029082272
},
{
"epoch": 0.0873758865248227,
"grad_norm": 10.575953483581543,
"loss": 6.5358,
"lr": 0.000614,
"step": 308,
"tokens_trained": 0.029273352
},
{
"epoch": 0.08794326241134752,
"grad_norm": 9.089850425720215,
"loss": 6.5088,
"lr": 0.0006180000000000001,
"step": 310,
"tokens_trained": 0.029463848
},
{
"epoch": 0.08851063829787234,
"grad_norm": 9.090002059936523,
"loss": 6.4849,
"lr": 0.000622,
"step": 312,
"tokens_trained": 0.029653272
},
{
"epoch": 0.08907801418439716,
"grad_norm": 12.038308143615723,
"loss": 6.4624,
"lr": 0.000626,
"step": 314,
"tokens_trained": 0.029841928
},
{
"epoch": 0.08964539007092198,
"grad_norm": 9.073866844177246,
"loss": 6.4515,
"lr": 0.00063,
"step": 316,
"tokens_trained": 0.030029808
},
{
"epoch": 0.0902127659574468,
"grad_norm": 8.727197647094727,
"loss": 6.43,
"lr": 0.000634,
"step": 318,
"tokens_trained": 0.030221288
},
{
"epoch": 0.09078014184397164,
"grad_norm": 14.558151245117188,
"loss": 6.4487,
"lr": 0.000638,
"step": 320,
"tokens_trained": 0.030410872
},
{
"epoch": 0.09134751773049646,
"grad_norm": 9.98914623260498,
"loss": 6.4279,
"lr": 0.000642,
"step": 322,
"tokens_trained": 0.030602376
},
{
"epoch": 0.09191489361702128,
"grad_norm": 10.395442962646484,
"loss": 6.4311,
"lr": 0.000646,
"step": 324,
"tokens_trained": 0.030792968
},
{
"epoch": 0.0924822695035461,
"grad_norm": 10.8250093460083,
"loss": 6.3726,
"lr": 0.0006500000000000001,
"step": 326,
"tokens_trained": 0.030982944
},
{
"epoch": 0.09304964539007092,
"grad_norm": 9.73416805267334,
"loss": 6.34,
"lr": 0.0006540000000000001,
"step": 328,
"tokens_trained": 0.031174928
},
{
"epoch": 0.09361702127659574,
"grad_norm": 8.596503257751465,
"loss": 6.3322,
"lr": 0.0006580000000000001,
"step": 330,
"tokens_trained": 0.031364288
},
{
"epoch": 0.09418439716312056,
"grad_norm": 8.49472427368164,
"loss": 6.3096,
"lr": 0.000662,
"step": 332,
"tokens_trained": 0.03155376
},
{
"epoch": 0.0947517730496454,
"grad_norm": 7.857503414154053,
"loss": 6.2368,
"lr": 0.000666,
"step": 334,
"tokens_trained": 0.031744368
},
{
"epoch": 0.09531914893617022,
"grad_norm": 9.007513999938965,
"loss": 6.198,
"lr": 0.00067,
"step": 336,
"tokens_trained": 0.031934136
},
{
"epoch": 0.09588652482269504,
"grad_norm": 8.185524940490723,
"loss": 6.2328,
"lr": 0.000674,
"step": 338,
"tokens_trained": 0.032124984
},
{
"epoch": 0.09645390070921986,
"grad_norm": 8.784396171569824,
"loss": 6.1945,
"lr": 0.0006780000000000001,
"step": 340,
"tokens_trained": 0.032316016
},
{
"epoch": 0.09702127659574468,
"grad_norm": 8.642311096191406,
"loss": 6.218,
"lr": 0.0006820000000000001,
"step": 342,
"tokens_trained": 0.032506224
},
{
"epoch": 0.0975886524822695,
"grad_norm": 8.493780136108398,
"loss": 6.194,
"lr": 0.0006860000000000001,
"step": 344,
"tokens_trained": 0.032696152
},
{
"epoch": 0.09815602836879432,
"grad_norm": 9.120508193969727,
"loss": 6.2241,
"lr": 0.00069,
"step": 346,
"tokens_trained": 0.032885688
},
{
"epoch": 0.09872340425531916,
"grad_norm": 9.34500503540039,
"loss": 6.1548,
"lr": 0.000694,
"step": 348,
"tokens_trained": 0.03307568
},
{
"epoch": 0.09929078014184398,
"grad_norm": 7.483356952667236,
"loss": 6.1282,
"lr": 0.0006979999999999999,
"step": 350,
"tokens_trained": 0.033267208
},
{
"epoch": 0.0998581560283688,
"grad_norm": 7.974069118499756,
"loss": 6.1032,
"lr": 0.0007019999999999999,
"step": 352,
"tokens_trained": 0.033458144
},
{
"epoch": 0.10042553191489362,
"grad_norm": 8.247384071350098,
"loss": 6.1698,
"lr": 0.0007059999999999999,
"step": 354,
"tokens_trained": 0.033650352
},
{
"epoch": 0.10099290780141844,
"grad_norm": 8.554885864257812,
"loss": 6.1429,
"lr": 0.00071,
"step": 356,
"tokens_trained": 0.033840232
},
{
"epoch": 0.10156028368794326,
"grad_norm": 7.209281921386719,
"loss": 6.0997,
"lr": 0.000714,
"step": 358,
"tokens_trained": 0.034030032
},
{
"epoch": 0.10212765957446808,
"grad_norm": 8.660383224487305,
"loss": 6.1497,
"lr": 0.000718,
"step": 360,
"tokens_trained": 0.034218592
},
{
"epoch": 0.10269503546099291,
"grad_norm": 9.382761001586914,
"loss": 6.0665,
"lr": 0.000722,
"step": 362,
"tokens_trained": 0.034408408
},
{
"epoch": 0.10326241134751774,
"grad_norm": 6.915714263916016,
"loss": 6.0636,
"lr": 0.000726,
"step": 364,
"tokens_trained": 0.034600016
},
{
"epoch": 0.10382978723404256,
"grad_norm": 7.8990631103515625,
"loss": 6.0975,
"lr": 0.00073,
"step": 366,
"tokens_trained": 0.034790792
},
{
"epoch": 0.10439716312056738,
"grad_norm": 8.859809875488281,
"loss": 6.0754,
"lr": 0.000734,
"step": 368,
"tokens_trained": 0.034981304
},
{
"epoch": 0.1049645390070922,
"grad_norm": 7.392801761627197,
"loss": 6.039,
"lr": 0.000738,
"step": 370,
"tokens_trained": 0.03516956
},
{
"epoch": 0.10553191489361702,
"grad_norm": 9.427324295043945,
"loss": 6.084,
"lr": 0.000742,
"step": 372,
"tokens_trained": 0.035358816
},
{
"epoch": 0.10609929078014184,
"grad_norm": 7.168910503387451,
"loss": 6.0498,
"lr": 0.000746,
"step": 374,
"tokens_trained": 0.035548016
},
{
"epoch": 0.10638297872340426,
"eval_loss": 6.038269996643066,
"eval_runtime": 21.3445,
"step": 375,
"tokens_trained": 0.035644104
}
],
"logging_steps": 2,
"max_steps": 7650,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 125,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}